Metraipolis › archive › dc_96da5d7f3ca8
Look Before You Prompt, and After: Scaffolding Human-AI Collaboration in Software Tutorial Creation — arXiv:2609.05563
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.05563
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T13:46:52.018Z
- SHA-256 of the archived text
6c9e39bd62587cccdcf2b8cf6000493ccc503078da49e7941bf7c4318c400d9e- Stable URL of this page
https://metraipolis.com/documento/dc_96da5d7f3ca8
How to cite
Look Before You Prompt, and After: Scaffolding Human-AI Collaboration in Software Tutorial Creation — arXiv:2609.05563 — arXiv (en), https://arxiv.org/abs/2609.05563 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_96da5d7f3ca8 (Metraipolis archive dc_96da5d7f3ca8, sha256 6c9e39bd62587cccdcf2b8cf6000493ccc503078da49e7941bf7c4318c400d9e)
BibTeX
@misc{dc96da5d7f3ca8,
title = {Look Before You Prompt, and After: Scaffolding Human-AI Collaboration in Software Tutorial Creation — arXiv:2609.05563},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.05563},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_96da5d7f3ca8; sha256 6c9e39bd62587cccdcf2b8cf6000493ccc503078da49e7941bf7c4318c400d9e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.05563. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
With LLMs, creating software tutorials now involves steering the model's output and shaping it into a coherent, accurate learning resource, yet existing LLM tools offer writers little support for this work. By analyzing interviews with technical writers ($N=17$), we identify three requirements for how they assemble and structure multiple LLM responses, curate the context the model uses, and verify the generated content. We designed a tool called dBlocks with the following features: blocks to scope content, a context manager to edit context, and inline execution to verify code. Following a human-centered design method, we iteratively refined the design through a user study ($N=5$). In a within-subjects lab study ($N=16$) comparing dBlocks with participants' preferred workflows for LLM-assisted authoring, participants reported significantly higher confidence in the tutorials they produced with dBlocks. In addition, the tool reduced friction in verification, with writers verifying code as they drafted rather than deferring or skipping it, and helped them avoid searching long chat histories by scoping their work into blocks that kept each tutorial section and its LLM conversation together. More broadly, our work offers implications for tools that scaffold human-AI collaboration in SE workflows and shows how human-centered design can guide the development of LLM-integrated tools. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.HC). Categorie arXiv: Software Engineering (cs.SE) ; Human-Computer Interaction (cs.HC). Pagina del lavoro: https://arxiv.org/abs/2609.05563 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-16T13:28:43.161Z dalla pagina https://arxiv.org/catchup/cs.HC/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).